US10263836B2 - Identifying troubleshooting options for resolving network failures - Google Patents

Identifying troubleshooting options for resolving network failures Download PDF

Info

Publication number
US10263836B2
US10263836B2 US14/223,995 US201414223995A US10263836B2 US 10263836 B2 US10263836 B2 US 10263836B2 US 201414223995 A US201414223995 A US 201414223995A US 10263836 B2 US10263836 B2 US 10263836B2
Authority
US
United States
Prior art keywords
failure
alarm
troubleshooting
network
operator
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US14/223,995
Other languages
English (en)
Other versions
US20150271008A1 (en
Inventor
Navendu Jain
Rahul Potharaju
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Microsoft Technology Licensing LLC
Original Assignee
Microsoft Technology Licensing LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Microsoft Technology Licensing LLC filed Critical Microsoft Technology Licensing LLC
Assigned to MICROSOFT CORPORATION reassignment MICROSOFT CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: POTHARAJU, RAHUL, JAIN, NAVENDU
Priority to US14/223,995 priority Critical patent/US10263836B2/en
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC reassignment MICROSOFT TECHNOLOGY LICENSING, LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: MICROSOFT CORPORATION
Priority to RU2016137896A priority patent/RU2682018C2/ru
Priority to CN201580015257.7A priority patent/CN106165345B/zh
Priority to PCT/US2015/021360 priority patent/WO2015148234A1/en
Priority to JP2016558574A priority patent/JP6959736B2/ja
Priority to EP15717299.0A priority patent/EP3123666B1/de
Priority to BR112016020189-2A priority patent/BR112016020189B1/pt
Publication of US20150271008A1 publication Critical patent/US20150271008A1/en
Priority to US16/357,202 priority patent/US11057266B2/en
Publication of US10263836B2 publication Critical patent/US10263836B2/en
Application granted granted Critical
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0686—Additional information in the notification, e.g. enhancement of specific meta-data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
    • G06F11/079—Root cause analysis, i.e. error or fault diagnosis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
    • H04L41/0659—Management of faults, events, alarms or notifications using network fault recovery by isolating or reconfiguring faulty entities
    • H04L41/0661—Management of faults, events, alarms or notifications using network fault recovery by isolating or reconfiguring faulty entities by reconfiguring faulty entities
    • H04L41/0672—
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/069—Management of faults, events, alarms or notifications using logs of notifications; Post-processing of notifications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0876—Aspects of the degree of configuration automation
    • H04L41/0886—Fully automatic configuration

Definitions

  • a data center is a collection of computing devices that communicate with one another over a network and operate in conjunction to provide computing services and/or data storage services to one or more end users, where an end user can be an individual, an enterprise, or the like.
  • the data center therefore includes numerous computing devices, numerous network infrastructure devices, such as routers, re-routers, switches, gateways, firewalls, virtual private networks (VPNs), bridges, etc., communications links between computing devices and network infrastructure devices, and communications links between network infrastructure devices.
  • VPNs virtual private networks
  • the network infrastructure devices include high-end devices, which tend to be relatively expensive.
  • data centers have been configured to include numerous commodity (e.g., off-the-shelf) network infrastructure devices to decrease capital costs associated with the data center. While these commodity devices cost less than the “high-end” devices, commodity devices tend to be somewhat less reliable than the high-end devices, resulting in an increased burden on data center operators to ensure uninterrupted service.
  • Resolving network failures can be complex and thus time-consuming, as network infrastructure devices in a data center can be manufactured by numerous different manufacturers, as computing and/or network devices in the data center may have different operating systems installed thereon, as a manufacturer may generate different models of the same type of device, etc. Thus, there is a significant amount of heterogeneity in conventional data centers.
  • an operations team is employed to ensure that the computing services and storage services promised to end users (e.g., in Service Level Agreements) are being met.
  • a network device e.g., a computing device or a network infrastructure device
  • the alarm is directed towards an operator console monitored by an operator on the operations team.
  • the operator reviews the alarm and, based upon personal knowledge and experience (and possibly some static guidelines), the operator performs troubleshooting and debugging to try to either only mitigate (rather than diagnose) or fix the failure (by diagnosing the problem root cause) indicated by the alarm. While this approach may be suitable for relatively small data centers, such approach does not scale. For example, data centers are scaling to include hundreds of thousands of computing devices and several thousand network infrastructure devices.
  • Described herein are various technologies pertaining to identifying potential troubleshooting options and resolution steps that can be employed to resolve a network failure in a data center.
  • the troubleshooting options and resolutions steps are provided to an operator, who can consume the troubleshooting options and resolutions steps and resolve the network failure using the provided troubleshooting options and resolutions steps.
  • Additionally described herein are various technologies pertaining to prioritizing network failures based upon alarms generated by devices in a data center, wherein a prioritized list can be surfaced to the operator to facilitate triaging alarms.
  • a data center includes a plurality of networked computing devices, wherein data can be transmitted between the computing devices over network links by way of a plurality of network infrastructure devices, such as routers, co-routers, switches, load balancers, firewalls, virtual private networks (VPNs), amongst others.
  • the computing devices and/or network infrastructure devices can be configured to generate alarms that are indicative of network failures.
  • a switch can be configured to generate an alarm when the switch detects that a link between the switch and another device is down. The alarm is received, and a determination is made as to whether the alarm is indicative of an actionable network event (e.g., a network failure that is to be resolved).
  • the failure conditions and associated telemetry data can be mapped to a set of observed symptoms experienced on: 1) the failing device or link; 2) the platform of the failing device; 3) devices neighboring the failing device in the network topography; 4) devices sharing a property with the failing device; and/or 5) devices in the same data center as the failing device, among other aspects.
  • at least one symptom e.g., “device down”, “link flapping”, “high CPU utilization”, . . .
  • at least one symptom can be identified for the failing device or link.
  • a plurality of recommended troubleshooting options that may potentially resolve the network failure can be identified.
  • the troubleshooting options can be based upon previous troubleshooting options observed in the past to resolve the network failure pertaining to the failing device or link, the failing device type, the failing device platform, etc.
  • the troubleshooting options can have respective labels assigned thereto, wherein the labels are indicative of respective probabilities that the troubleshooting options, when taken by the operator, will resolve the network failure indicated by the alarm.
  • the labels can be identified based upon past successes or failures of the troubleshooting options when undertaken with respect to the failing device or link, the failing device type, the failing device platform, etc.
  • the operator can be provided with a list of troubleshooting options to resolve the network failure, as well as labels respectively assigned to the troubleshooting options that are indicative of respective probabilities that the troubleshooting options will resolve the network failure. Further, the operator can employ domain knowledge (e.g., from experience or knowledge provided by a domain expert) in combination with the probabilities of the troubleshooting option to determine the sequence of actions to perform to resolve the failure.
  • domain knowledge e.g., from experience or knowledge provided by a domain expert
  • a plurality of debugging steps can be presented to the operator, wherein the debugging steps can be assigned labels that are respectively indicative of probabilities that the debugging steps will correct the network failure.
  • a network infrastructure device can output an alarm that indicates that a downstream network infrastructure device is not replying to heartbeat requests. The alarm can be received, and the failure conditions in the alarm can be mapped to the previously observed symptom “device down.” For such symptom, three troubleshooting options, ranked by their respective probabilities of resolving the failure, can be presented to the operator: 1) “check cable”, 2) “check power supply”, and 3) “check network card”.
  • Labels assigned to the troubleshooting options can indicate that the first troubleshooting option is most likely to resolve the network failure, the second troubleshooting option is second most likely to resolve the network failure, and the third troubleshooting option is third most likely to resolve the network failure.
  • at least one debugging step can be provided to the operator. For example, for the troubleshooting option “check cable”, two potential debugging steps can be presented to the operator. Each debugging step can be assigned a respective label that is indicative of a probability that the debugging step will resolve the network failure.
  • debugging steps of “reseat the cable” and “clean the cable” can be presented as debugging steps, with the first debugging step indicated as being more likely to correct the network failure than the second debugging step.
  • the indication of likelihood can be a function of probabilities computed based upon observed debugging steps previously undertaken by data center operators on the failing device or link or device(s) related to the failing device or link.
  • a data-driven approach can be used to identify the troubleshooting options and debugging steps, and to assign respective labels to troubleshooting options and debugging steps. For example, when the operator resolves the network failure by way of a troubleshooting option and corresponding debugging step, the operator can provide feedback that indicates if the symptom was correctly identified, can identify which troubleshooting option was selected, and can identify which debugging steps were used to resolve the network failure. Accordingly, when a different alarm is subsequently received (pertaining to the failing device or link, the type of the failing device, the platform of the failing device, etc.), the failure conditions can be appropriately mapped to a symptom, and labels assigned to troubleshooting options and debugging steps, respectively, can be updated based upon this feedback. Thus, over time, accuracy of the troubleshooting options and debugging steps can increase.
  • alarms can be grouped to represent a singular network failure, and network failures can be prioritized. That is, instead of treating low-level network alarms in isolation, alarms can be correlated (grouped) with one another to represent a singular network failure.
  • this grouping can be based upon three criteria: 1) time; a first alarm generated by a first device can be grouped with a second alarm generated recently in time by the first device or a second device on the same interface; 2) location; the first alarm can be grouped with a second alarm generated by a second device that is a neighbor of the first device in the network (e.g., 1-2 hops upstream or downstream in the hierarchical network topography); and 3) redundancy group; the first alarm can be grouped with a second alarm generated by a second device in a same redundancy group as the first device (e.g., which can indicate a problem with a failover protocol).
  • Grouping of alarms to represent network failures can be employed to categorize and rank current network failures, such that network failures that may result in high business impact can be prioritized higher than network failures that result in low business impact.
  • FIG. 1 illustrates an exemplary portion of a data center.
  • FIG. 2 illustrates an exemplary data center architecture
  • FIG. 3 is a functional block diagram of an exemplary resolution system that receives alarms generated by network devices in a data center and outputs troubleshooting options and debugging steps responsive to receiving the alarms.
  • FIG. 4 is a functional block diagram of an exemplary resolution identifier component included in the resolution system.
  • FIG. 5 is an exemplary failure history table.
  • FIG. 6 is an exemplary graphical user interface that depicts potential troubleshooting options and debugging steps for resolving a network failure indicated by an alarm.
  • FIG. 7 illustrates an exemplary alarm prioritizer component that is optionally included in the resolution system.
  • FIG. 8 is a flow diagram that illustrates an exemplary methodology for outputting troubleshooting options for resolving a network failure indicated by an alarm generated by a network device.
  • FIG. 9 is a flow diagram that illustrates an exemplary methodology for first grouping related alarms and then outputting a ranked list of network failures.
  • FIG. 10 is a flow diagram that illustrates an exemplary methodology for updating historical data pertaining to a data center based upon operator feedback.
  • FIG. 11 is an exemplary computing system.
  • the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless specified otherwise, or clear from the context, the phrase “X employs A or B” is intended to mean any of the natural inclusive permutations. That is, the phrase “X employs A or B” is satisfied by any of the following instances: X employs A; X employs B; or X employs both A and B.
  • the articles “a” and “an” as used in this application and the appended claims should generally be construed to mean “one or more” unless specified otherwise or clear from the context to be directed to a singular form.
  • the terms “component” and “system” are intended to encompass computer-readable data storage that is configured with computer-executable instructions that cause certain functionality to be performed when executed by a processor.
  • the computer-executable instructions may include a routine, a function, or the like. It is also to be understood that a component or system may be localized on a single device or distributed across several devices.
  • the term “exemplary” is intended to mean serving as an illustration or example of something, and is not intended to indicate a preference.
  • the data center 100 can be configured to provide services to an end user 102 , wherein such services can be compute services and/or storage services, and wherein the end user 102 can be an individual, an enterprise, or the like.
  • the data center 100 may be an enterprise data center that is owned by a particular enterprise and provides compute and storage services for the enterprise.
  • the end user 102 can be an individual who works in the enterprise, a division of the enterprise, etc.
  • the data center 100 may be operated by a first company, and the end user 102 may be a second company (e.g., the first company leases data storage and computing resources to the second company).
  • the data center 100 may be operated by a company, and the end user 102 may be an individual.
  • Exemplary computing services and/or storage services that can be offered by the data center 100 included email services, search services, storage, online services, and the like.
  • the end user 102 can operate a computing device 103 and can transmit data to and receive data from the data center 100 by way of the computing device 103 , wherein the computing device 103 can be any suitable type of computing device, including but not limited to a desktop computing device, a mobile computing device (e.g., a laptop computing device, a mobile telephone, a slate computing device, a wearable computing device, etc.), a server, or the like.
  • a desktop computing device e.g., a laptop computing device, a mobile telephone, a slate computing device, a wearable computing device, etc.
  • server e.g., a server, or the like.
  • the data center 100 includes a plurality of computing devices 104 - 110 , wherein the computing devices 104 - 110 may include servers, dedicated storage devices, etc.
  • the computing devices 104 - 110 are configured to perform actions (e.g., store data, process data, and/or transmit data) based upon a request from the computing device 103 of the end user 102 .
  • the end user 102 may request performance of a search over content in storage of the first computing device 104
  • the first computing device 104 can be configured to execute the search and output search results responsive to the data center 100 receiving the request.
  • the second computing device 106 can store a portion of a search engine index, and can be configured to transmit the portion of the search engine index to another computing device in the data center 100 (or to another data center) responsive to receipt of a request to do so from the computing device 103 .
  • the data center 100 further comprises a plurality of network infrastructure devices 114 - 120 .
  • the network infrastructure devices 114 - 120 are configured to facilitate transmission of data between computing devices in the computing devices 104 - 110 in the data center 100 , facilitate transmission of data between data centers, as well as to facilitate transmission of data between the computing device 103 operated by the end user 102 and the computing devices 104 - 110 .
  • the network infrastructure devices 114 - 120 include two switches 114 and 116 , a router 118 , and a firewall 120 .
  • Devices in the data center 100 are communicatively coupled to one another by way of network links
  • the first computing device 104 is communicatively coupled with the switch 114 by way of a first network link
  • the second computing device 106 is communicatively coupled with the switch 114 by way of a second network link
  • the switch 114 is communicatively coupled to the router 118 by way of a third network link, and so on.
  • the network infrastructure devices 114 - 120 can include hardware and/or software-based devices.
  • the router 118 may be a software-based router that is executed by a computing device.
  • the firewall 120 may be a software firewall that executes in a hardware router or computing device.
  • the computing devices 104 - 110 and/or the network infrastructure devices 114 - 120 can be configured to output alarms when certain respective events are detected.
  • the router 118 can be configured to output an alarm when the router 118 outputs heartbeat request (e.g., a request to reply to the message) directed towards a particular computing device and fails to receive one or more responses within a threshold amount of time from transmitting the heartbeat.
  • heartbeat request e.g., a request to reply to the message
  • a set of distributed processes running inside the data center 100 can periodically send a heartbeat request to a service, a server, or a computing device in addition to executing a set of synthetic micro-transactions to ensure that the service, server or the computing device is available from an end-user perspective (e.g., send a small test mail to check that the mail service is running properly).
  • An alarm can be generated when a response to the heartbeat request is not received. Accordingly, an alarm can be indicative of a network failure: e.g., that the computing device is down, or that a network link between the router 118 and the particular computing device is down.
  • the switch 114 can be configured to generate an alarm when data volume directed through the switch 114 reaches a pre-defined threshold.
  • a resolution system 122 receives alarms generated by the computing devices 104 - 110 and/or the network infrastructure devices 114 - 120 and outputs data to an operator station 124 employed by a network operator 126 to assist the network operator 126 in resolving network failures indicated by at least one alarm.
  • the resolution system 122 can identify a network failure based upon at least one received alarm, and can identify a plurality of potential troubleshooting options for resolving the network failure.
  • a troubleshooting option can be perceived as a high-level check that can be performed by the operator, such as “check network card”, “check cable”, or the like.
  • the resolution system 122 can assign respective labels to the troubleshooting options, where the labels are respectively indicative of probabilities that the troubleshooting options will resolve the network failure when undertaken by the network operator 126 .
  • the resolution system 122 can identify the troubleshooting options and respective labels based upon previous troubleshooting options undertaken by the network operator 126 (or other operators in an operations team for the data center 100 ) to resolve similar network failures (e.g., network failures with similar symptoms).
  • a troubleshooting option can have one or more debugging steps assigned thereto, wherein a debugging step provides more granular instructions (when compared to the troubleshooting option) to the operator 126 for resolving the network failure.
  • a list of debugging steps can be presented to the operator 126 .
  • each debugging step can have a respective label assigned thereto, where the label is indicative of a probability that the debugging step will resolve the identified network failure (assuming that the troubleshooting option is the correct option).
  • the operator 126 is provided with a list of troubleshooting options from which the operator 126 can select a particular troubleshooting option (e.g., the troubleshooting option associated with the highest probability of resolving the network failure), and can then perform debugging steps in order of probability.
  • the operator 126 can further be provided with counts indicating a number of times that a troubleshooting option and/or debugging step was taken and/or a number of times that the troubleshooting option and/or debugging step was successful. For instance, two troubleshooting options can be assigned equivalent probabilities (e.g., 50%).
  • a first label assigned to the first troubleshooting option can indicate that the troubleshooting option was taken twice and was successful once
  • a second label assigned to the second troubleshooting option can indicate that the troubleshooting option was selected one thousand times and was successful five hundred times.
  • the resolution system 122 can further be configured to prioritize network failures for the operator 126 , such that network failures are triaged. As will be understood by one skilled in the art, some network failures have greater impact on profit, data throughput, or the like, than other network failures.
  • the resolution system 122 can be configured to receive an alarm from the computing devices 104 - 110 and/or the network infrastructure devices 114 - 120 , and group the alarm with at least one other alarm to represent a singular network failure. Thus, instead of the operator 126 analyzing low-level independent alarms, the operator 126 can be provided with a higher-level representation of network failures. Further, the resolution system 122 can prioritize network failures relative to one another, such that the operator 126 is directed to troubleshoot network failures having highest impact first, followed by network failures having lower impact.
  • the resolution system 122 is shown as being included in the data center 100 , it is to be understood that the resolution system 122 may be executed on a computing device that is external to the data center 100 .
  • the data center 100 may include a computing device that is configured to transmit all collected network alarms to an external device that executes the resolution system 122 .
  • the resolution system 122 can be executed on a computing device or distributed across multiple computing devices.
  • the resolution system 122 may execute in a virtual machine (VM), wherein the VM is executed on a computing device or is distributed across multiple computing devices (internal or external to the data center 100 ).
  • VM virtual machine
  • the data center architecture 200 comprises a plurality of Top of Rack (ToR) switches 202 - 208 .
  • a respective plurality of rack-mounted servers can be connected (or dual-homed) to each ToR switch in the ToR switches 202 - 208 .
  • the architecture 200 also includes a primary aggregation switch 210 and a backup aggregation switch 212 , wherein each ToR switch in the ToR switches 202 - 208 is connected to the primary aggregation switch 210 and the backup aggregation switch 212 (for redundancy).
  • a data center includes several pairs of primary and backup aggregation switches, and each redundant pair of aggregation switches aggregates traffic from several (e.g., tens) of ToR switches.
  • the architecture 200 may include a first redundant pair of load balancers 214 - 216 connected to the primary aggregation switch 210 and a second redundant pair of load balancers 218 and 220 connected to the backup aggregation switch 212 .
  • the load balancers 214 - 220 can perform mapping between static IP addresses (e.g., exposed to clients through DNS) and dynamic IP addresses of servers that process user requests.
  • the architecture 200 further includes a primary access router 222 and a backup access router 224 .
  • the primary aggregation switch 210 , the backup aggregation switch 212 , the primary access router 222 , and the backup access router 224 can form a redundancy group. In a data center having the architecture 200 , redundant groups of devices and links can be used to mask network failures.
  • the aggregation switches 210 - 212 forward traffic (aggregated from the ToRs 202 - 208 ) to the access routers 222 - 224 .
  • the architecture 200 also includes a primary core router 226 and a backup core router 228 , each of which are connected to both access routers 222 - 224 .
  • the primary access router 222 , the backup access router 224 , the primary core router 226 , and the backup core router 228 form another redundancy group.
  • the access routers 222 - 224 route, for example, aggregated traffic from up to several thousand servers and route the traffic to the core routers 226 - 228 .
  • the core routers 226 - 228 connect to the rest of the data center network and Internet 230 .
  • servers in the architecture can be partitioned into virtual local area networks (VLANs) to limit overhead and to isolate different applications hosted in the network.
  • VLANs virtual local area networks
  • redundancy e.g., 1:1 redundancy
  • the architecture 200 can include middle boxes such as load balancers, firewalls, and the like. From the foregoing, it can be ascertained that the computing devices 104 - 110 can be server computing devices in the architecture, the switches 114 - 116 can be aggregation switches, the router 118 can be an access router or a core router, etc.
  • the resolution system 122 can receive alarms generated by multiple devices in the data center 100 at different points in time.
  • the resolution system 120 includes an alarm receiver component 302 that receives the alarms generated by the devices in the data center 100 .
  • a resolution identifier component 304 is in communication with the alarm receiver component 302 , and is configured to ascertain whether the alarm received by the alarm receiver component 302 is indicative of an actionable network failure (e.g., a network failure that the operator 126 can resolve via troubleshooting and debugging).
  • an actionable network failure e.g., a network failure that the operator 126 can resolve via troubleshooting and debugging.
  • an alarm generated by the router 118 can indicate that the router 118 is unable to communicate with the switch 116 , which can in turn (for example) indicate any of 1) the router malfunctioning 2) the switch being down; 3) loose cabling on the network link between the router 118 and the switch 116 ; etc.
  • actionable network failures that can be resolved by the operator 126 .
  • the resolution system 122 can include or have access to a data store 306 that comprises historical data 308 .
  • the historical data 306 can comprise “failure history tables” for devices and links in the data center 100 , wherein a failure history table for a device or link can include information that is descriptive of past failures of the device or link, including failure symptoms, times of most recent failure, number of failures over a threshold period of time, configuration changes, and the like.
  • the alarm receiver component 302 receives an alarm, which includes failure conditions.
  • the failure conditions can include time of generation of the alarm, identity of the device or link that exhibits a failure symptom, identity of the device that generated the alarm, identification of an interface that corresponds to a detected event, identity of a data center that includes the device or link that exhibits the failure symptom, etc.
  • the resolution identifier component 304 based upon the alarm (and optionally other received alarms), can determine that the alarm is indicative of an actionable network failure, and can further identify a failing device or link based upon the contents of the alarm (e.g., in some cases the device that generates the alarm is not the failing device).
  • the resolution identifier component 304 can map the failure conditions indicated in the alarm and associated telemetry data to a set of previously observed failure symptoms included in the historical data 308 .
  • the failing device or link may have previously exhibited the failure symptoms
  • a device of the same type as the failing device may have previously exhibited the failure symptoms
  • a device sharing a platform with the failing device may have previously exhibited the failure symptoms
  • a neighboring device in the network e.g., 1-2 hops upstream or downstream from the failing device
  • the resolution identifier component 304 can perform a statistical analysis over the historical data 308 to identify a plurality of recommended troubleshooting options, as well as debugging steps that respectively correspond to the troubleshooting options, for use by the operator 126 to resolve the network failure. Further, the troubleshooting options and associated debugging steps can each be ranked by confidence, such that troubleshooting options and debugging steps with highest confidence of resolving the network problem are presented most prominently to the operator 126 .
  • the resolution identifier component 304 can determine that a network alarm generated by the switch 116 indicates that the third computing device 108 in the data center 100 is not responding to heartbeat requests, which can be mapped to, for example, the following previously observed failure symptoms for the third computing device 108 (or other devices in the data center 100 or in another data center): 1) “link flapping”; and 2) “device down”. For each of such symptoms identified by the resolution identifier component 304 , the resolution identifier component 304 can identify troubleshooting options and corresponding debugging steps in the historical data 308 indicated as previously being performed to resolve network failures that have such a symptom.
  • the resolution identifier component 304 can assign labels to the troubleshooting options and debugging steps that are respectively indicative of probabilities that the troubleshooting options and debugging steps will mitigate the network failure.
  • An exemplary structure of data in the historical data 308 that facilitates identifying of the symptoms, the troubleshooting options, debugging steps, and labels is described in further detail below.
  • the resolution identifier component 304 can then output the symptoms, the troubleshooting options, the debugging steps, and the corresponding labels to the operator 126 . Effectively, then, the operator 126 is provided with a prioritized list of troubleshooting options and resolution steps for each symptom that is mapped to the failure conditions of the received alarm (which is indicative of an actionable network failure). The operator 126 may then step through troubleshooting options and debugging steps in an order based upon the labels assigned to the troubleshooting options and debugging steps, resulting in relatively efficient resolution of the network failure.
  • the resolution identifier component 304 can identify at least one troubleshooting option and at least one debugging step, and can transmit a signal to a device in the data center 100 that causes the at least one troubleshooting option to be selected and the at least one debugging step to be performed, without intervention from the operator 126 .
  • the resolution identifier component 304 can determine that there is a relatively high probability that rebooting the switch 116 will mitigate an observed network failure symptom.
  • the resolution identifier component 304 can transmit a signal to the switch 116 that causes the switch 116 to be rebooted, without surfacing the alarm to the operator 126 or otherwise requiring operator intervention.
  • the resolution identifier component 304 can attempt to automatically resolve a network failure prior to surfacing troubleshooting options and debugging steps to the operator 126 when 1) a computed probability of a troubleshooting option and debugging step resolving the network failure is above a predefined probability threshold (e.g., 0.9); 2) the computed probability of the troubleshooting option and debugging step resolving the network failure is among a k-highest probabilities for troubleshooting options and debugging steps resolving the network failure (e.g., among the three troubleshooting options and debugging steps that are most probable to resolve the network failure); 3) automatic selection of the troubleshooting option and performance of the debugging step does not result in a redundancy failure; 4) automatic selection of the troubleshooting option and performance of the debugging step does not take more than a threshold amount of time (e.g., one minute); and/or 5) automatic selection of the troubleshooting option and performance debugging step
  • the resolution identifier component 304 can further be configured to surface additional data pertaining to network failures to the operator 126 .
  • the resolution identifier component 304 can query the historical data 308 to aggregate failure data across a variety of dimensions.
  • the resolution identifier component 304 can output data that is indicative of a number of times that the device or link has failed (e.g., over a threshold historical time window), frequency of the device or link failing relative to frequency of other devices or links in the data center 100 failing, frequency of the device failing relative to frequency of other devices of the same type in the data center 100 failing, etc.
  • the operator 126 can set forth a request for information pertaining to a particular device type, platform, or data center, and the resolution identifier component 304 can aggregate failure data across a variety of parameters to surface failure information for the operator 126 .
  • the resolution identifier component 304 responsive to receiving a request from the operator 126 for information about a device platform, can output data that identifies most frequently failing devices on that platform, frequency of device failure on the platform relative to other platforms, frequency of failures of devices of different types relative to one another, etc.
  • the operator 126 can request surfacing of information about a data center dimension/axis, rather than a specified device or device type. For instance, the operator 126 can request identification of most frequently failing devices in the data center 100 , and the resolution identifier component 304 can return a list of devices in the data center 100 that fail most frequently. Similarly, the operator 126 can request identification of most stable devices in the data center 100 , and the resolution identifier component 304 can return a list of devices in the data center 100 that fail least frequently.
  • the structure of the historical data 308 facilitates aggregation of information about numerous dimensions/axes.
  • the resolution system 122 may also include a feedback component 312 that is configured to receive feedback from the operator 126 as to symptoms observed for a failing device, troubleshooting options and/or debugging steps undertaken to correct a network failure caused by the failing device, amongst other information.
  • the feedback component 312 responsive to receiving input from the operator 126 , may then be configured to update the historical data 308 (e.g., a historic failure table for the failing device).
  • the resolution identifier component 304 can output updated failure symptoms, troubleshooting options, debugging steps, and/or labels based upon the recent observations of the operator 126 .
  • the resolution system 122 may optionally include an event prioritizer component 314 that prioritizes actionable network failures for presentation to the operator 126 .
  • an event prioritizer component 314 that prioritizes actionable network failures for presentation to the operator 126 .
  • numerous devices in the data center 100 may generate alarms, conventionally requiring the operator 126 to parse through a large volume of alarms to determine which alarms represent actionable network failures, and to further prioritize network failures.
  • the event prioritizer component 314 lessens the burden on the operator 126 by correlating several alarms to represent a singular network failure, and prioritizing network failures (e.g., as a function of impact of the network failure).
  • the data store 306 can include a network graph 310 , which is representative of a hierarchical network topography of the data center 100 , and the event prioritizer component 314 can prioritize network failures based upon the network graph 310 .
  • a network failure caused by a device close to the top of the network hierarchy poses a high risk of service outage and can, therefore, be prioritized higher than network failures caused by devices lower in the network hierarchy.
  • the event prioritizer component 312 can prioritize network failures as a function of a number of properties that may be impacted due to the respective network failures (or even a single property with a risk of high business intelligence impact).
  • the resolution identifier component 304 receives an alarm 400 generated by a device in the data center 100 .
  • the device may be one of the computing devices 104 - 110 or one of the network infrastructure devices 114 - 120 .
  • the device may be one of the computing devices 104 - 110 or one of the network infrastructure devices 114 - 120 .
  • the device may be one of the computing devices 104 - 110 or one of the network infrastructure devices 114 - 120 .
  • the alarm 400 includes a plurality of failure conditions: 1) a timestamp that indicates when the alarm was generated by the device; 2) an alarm ID that identifies a unique alarm generated from a device; 3) a device ID that identifies the device that generated the alarm; 4) an interface link that identifies a particular port or network link that is experiencing a failure; and 5) and an event description, which includes machine generated text providing more details on the failure and is output by the device that generated the alarm 400 . It is to be understood that content of the alarm 400 can differ from what is shown in FIG. 4 and described herein.
  • the resolution identifier component 304 receives the alarm 400 and, in an exemplary embodiment, can determine whether the alarm is indicative of an actionable network failure.
  • the resolution identifier component 304 includes a failure identifier component 402 that analyzes the alarm 400 and can identify that the alarm 400 represents an actionable network failure, and can further identify a failing device or link (e.g., based upon the device ID and/or the network graph 310 ).
  • the device that generated the alarm 400 (the generating device) may be operating properly; however, a network infrastructure device (the failing device) connected to the device that generated the alarm (e.g., by way of the interface link identified in the alarm 400 ) may be failing.
  • the event description in the alarm 400 can indicate that the device identified by the device ID is not responding to heartbeat requests over a particular network link.
  • the failure identifier component 402 can assign metadata to the alarm 400 that is indicative of severity of a network failure indicated by the alarm.
  • the failure identifier component 402 can identify traffic loss that is caused by the device or link failing.
  • the failure identifier component 402 can assign one of a plurality of predefined values to the alarm 400 based upon a volume of traffic loss that may be caused by an event represented by the alarm 400 .
  • the failure identifier component 402 can assign one of “high”, “medium”, or “low” to the alarm 400 to represent severity of the network alarm. Pursuant to an example, this value can be placed in a device failure history table and/or a link failure history table.
  • the failure identifier component 402 can assign a value to the alarm 400 that is indicative of risks related to redundancy in the data center 100 .
  • the value can indicate whether the failure represented by the alarm 400 causes traffic loss within a redundancy group.
  • a troubleshooting option can be automatically selected and a debugging step can be automatically performed to auto-triage the failure event represented by the alarm 400 .
  • Exemplary values can include “redundancy successful”, “redundancy failure”, or “redundancy at risk”, wherein “redundancy at risk” can indicate that the failing device or link is single legged.
  • the resolution identifier component 304 further includes a mapper component 404 . Responsive to the failure identifier component 402 identifying the failing device or link, the mapper component 404 can access the historical data 308 and map the failure conditions (and associated telemetry data) indicated in the alarm 400 (or a group of correlated alarms that are representative of the network failure) to at least one previously observed symptom represented in the historical data 308 .
  • the historical data 308 can comprise a plurality of device failure history tables 406 - 408 and a plurality of link failure history tables 410 - 412 , wherein each failure history table in the device failure history tables 406 - 408 is for a respective device in the data center 100 , and each failure history table in the link failure history tables 410 - 412 is for a respective link in the data center 100 .
  • the historical data 308 can include failure history tables for devices/links in other data centers.
  • the failure history tables 406 - 412 can be distributed over numerous storage devices.
  • the first device failure history table 406 can include historic failure information for a first device in the data center 100 .
  • This failure information can include, but is not limited to including: 1) data that is descriptive of the first device, including identity of the first device, manufacturer of the first device, type of the first device, model of the first device, platform of the first device, etc.; 2) availability of the first device over time (and amount of time that has passed since a most recent failure); 3) network monitoring data, such as traffic passing through the first device, current CPU and memory utilization of the first device, CPU utilization of the first device over time, memory utilization of the first device over time, a number of connections of the first device, etc.; 4) data indicative of configuration changes made to the first device; 5) observed failure symptoms for the first device, troubleshooting options previously employed to alleviate the failure symptoms, and debugging steps previously taken to resolve the failure symptoms; 6) hardware and software changes performed on the first device; 7) identities of engineers and operators who have historically worked on the device; and 8) number of out-of-warranty component replacement
  • the first link failure history table 410 can include historic failure data for a first link in the data center.
  • This failure information can include, but is not limited to including, 1) data that is descriptive of the first link, including identity of the first link, devices connected via the first link, manufactures of such devices/links, platforms of such devices, etc.; 2) availability of the first link over time (and amount of time that has passed since a most recent failure); 3) network monitoring data, such as current traffic passing over the link, historic traffic over the link, etc.; 4) data indicative of configuration changes to devices coupled via the link; 5) observed failure symptoms for the link, troubleshooting options previously employed to alleviate the failure symptoms, and debugging steps previously taken to resolve the failure symptoms; 6) hardware and software changes performed on devices connected via the link, 7) type of link e.g., copper vs. optical, 8) capacity of link etc.
  • the mth link failure history table 412 can include analogous information.
  • the mapper component 408 can receive the alarm 400 and map failure conditions in the alarm 400 to at least one observed symptom for the failing device identified in at least one of the device failure history tables 406 - 408 or the link failure history tables 410 - 412 .
  • the mapper component 404 can initially access the failure history table of the failing device, and ascertain if the failure conditions map to previously observed failure symptoms for the failing device.
  • the mapper component 404 can then expand the search to neighboring devices in the network and/or devices of the same type and/or model as the failing device to identify previously observed failure symptoms that map to the failure conditions indicated in the alarm 400 .
  • the mapper component 404 can map the failure conditions of the alarm 400 to previously observed symptoms: 1) “device down”; and 2) “link flapping” for the failing device, as identified in the failure history table for the failing device.
  • the resolution identifier component 304 further includes a label assignor component 414 that identifies troubleshooting options identified in the historical data 308 as being previously undertaken to resolve the network failure symptom identified by the mapper component 404 .
  • the label assignor component 414 further assigns labels to respective troubleshooting options, wherein a label is indicative of a probability that the troubleshooting option will mitigate the network failure symptom.
  • the label assignor component 414 can initially search the device failure history table of the failing device (or a link failure history table for a failing link) to ascertain whether any troubleshooting options and/or debugging steps have been previously undertaken for the observed symptoms and device.
  • the label assignor component 414 may not need to perform further searching over the historical data 308 .
  • the label assignor component 414 can output the troubleshooting option without analyzing content of other failure history tables of other devices.
  • the label assignor component 414 can search failure history tables of other devices, such as neighboring devices in the network topology, devices by the same manufacturer, devices of the same type, etc. By searching over the failure history tables 406 - 412 in the historical data 308 , the label assignor component 414 can identify previously successful troubleshooting options and debugging steps, as well as respective confidence labels, for resolving the failure symptom.
  • the resolution identifier component 304 can further comprise an output component 416 that outputs the troubleshooting options, debugging steps, and corresponding labels.
  • the output component 416 can output such troubleshooting options, debugging steps, and labels to a display of the computing device 124 employed by the operator 126 .
  • the output component 416 can transmit the troubleshooting options, debugging steps, and labels to a different computing device.
  • the output component 416 can cause a troubleshooting option to be automatically selected and a debugging step to be automatically performed without operator intervention.
  • the output component 416 can also output (for a failing device or link), a summary failure history table for presentment to the operator 126 . This can provide the operator 126 with historical context pertaining to previous device or link failures.
  • the resolution identifier can maintain a summary failure history table for devices and/or links in the data center 100 , wherein an exemplary summary failure history table can include, but is not limited to including: 1) a name of the device or link; 2) an indication as to the failure rate of the device or link relative to other devices or links (e.g., an indication as to whether the device or link is a top-k problematic device); 3) recent changes made to the device or link (e.g., hardware, software, and/or configuration changes); 4) an amount of time since the last time the device or link failed; and 5) recent troubleshooting options selected and/or operators that performed troubleshooting.
  • an exemplary summary failure history table can include, but is not limited to including: 1) a name of the device or link; 2) an indication as to the failure rate of the device or link relative to other devices or links (e.g., an indication as to whether the device or link is a top-k problematic device); 3) recent changes made to the device or link (e.g., hardware, software, and
  • the graphical user interface 600 can be generated by the resolution identifier component 304 .
  • the graphical user interface includes a field 602 that presents the following information to the operator 126 pertaining to either the failing device identified by the failure identifier component 402 or a device otherwise of interest to the operator 126 : 1) the name of the failing device; 2) the model of the failing device; 3) an identity of the data center that includes the failing device; 4) a property of the failing device; 5) a type of the failing device; 6) recent hardware changes and recent software changes; and 7) links to tickets that describe these changes in more detail.
  • the graphical user interface 600 additionally includes a field 604 that illustrates previously observed symptoms that map to the contents of a received alarm (e.g., the alarm 400 ).
  • exemplary symptoms can include “link flap” and “device down.”
  • the field 604 also includes, for each observed symptom, a plurality of potential troubleshooting options. For example, for the “device down” system, the following troubleshooting options are displayed in the field 604 : 1) “check cable”; 2) “check power supply”; and 3) “check network card”.
  • the troubleshooting options have respective labels assigned thereto that are indicative of the probabilities that the respective troubleshooting options will alleviate the corresponding failure symptom.
  • the “check cable” troubleshooting option is assigned a label that indicates that there is a 60% probability that troubleshooting the failure symptom “device down” through utilization of at least one debugging step corresponding to such troubleshooting option will alleviate the problem.
  • the “check power supply” troubleshooting option can be assigned a label that indicates that there is a 25% probability that performing debugging step(s) corresponding to such troubleshooting option will result in alleviating the failure symptom.
  • each troubleshooting option has at least one debugging step corresponding thereto.
  • the troubleshooting option “check cable” has two debugging steps corresponding thereto (and illustrated in the graphical user interface 600 ): 1) “reseat cable”; and 2) “clean cable.” These debugging steps are also assigned labels that are indicative of respective probabilities that the resolution steps will resolve the failure symptom (when the parent troubleshooting option is selected).
  • some debugging steps may have further instructions assigned thereto to assist the operator 126 in performing the debugging steps.
  • further instructions can be presented to the operator 126 responsive to the operator selecting a graphical icon 606 in the graphical user interface 600 that is positioned adjacent to the aforementioned resolution step. This can result in a pop-up window 607 (or a separate window) to be displayed that provides the operator 126 with additional information about replacing the network card.
  • the additional information in an exemplary embodiment, can have hyperlinks assigned thereto, wherein selection of a hyperlink by the operator 126 can direct the operator to additional information.
  • the graphical user interface 600 may further include various fields 608 - 612 that can include graphical data (e.g., graphs) that are representative of various operating parameters of the failing device.
  • the field 608 can depict a graph that illustrates volume of traffic passing through the failing device over a particular window of time
  • the field 610 can depict a graph that is representative of availability of the failing device over a window of time
  • the field 612 can depicts a graph that illustrates points in time when the failing device was observed to have failed.
  • the graphical user interface 600 can also include features that facilitate receipt of feedback from the operator 126 .
  • a button 614 can be included in the graphical user interface 600 that, when selected, causes a window 616 to be presented to the operator 126 , where the window 126 includes several fields that can be populated by the operator 126 . This allows the operator 126 to identify symptoms observed when troubleshooting the failing device, a troubleshooting option employed by the operator 126 when troubleshooting the failing device, and debugging steps undertaken by the operator 126 when troubleshooting the failing device.
  • the graphical user interface 600 can also include a graphical object 618 that is representative of a topological view of a portion of the data center 100 , wherein the device identified in the field 602 can be represented as a center graphical icon 620 in the graphical object 618 , and devices one hop from the device identified in the field 602 can be represented by graphical icons 622 - 634 surrounding the central graphical icon 620 (e.g., with connections between graphical icons representing links therebetween). Furthermore, the graphical icons 620 - 634 can be color-coded to indicate the types of the respective devices represented by the graphical icons 620 - 634 .
  • the graphical icons 620 - 634 in the graphical object 618 can have respective shapes that are indicative of the types of the devices represented by the graphical icons.
  • a graphical icon shaped as a square can represent a core router
  • a graphical object shaped as a circle can represent a VPN, etc.
  • the graphical icons 620 - 634 in the graphical object 618 can be selectable, wherein selection of a graphical icon causes information about the device represented by the graphical icon to be set forth in the field 602 (and other fields in the graphical user interface 600 ).
  • shape of a graphical icon can represent a type of device represented by the icon, and color of the graphical icon can represent a manufacturer of the device. Other variants are also contemplated.
  • the event prioritizer component 312 can receive alarms generated by devices in the data center 100 .
  • the event prioritizer component 312 includes an alarm correlator component 700 , wherein the alarm correlator component 700 correlates alarms into respective groups, wherein the groups are representative of respective network failures.
  • the alarm correlator component 700 upon receipt of an alarm, can execute a search in the historical data 308 to identify recent alarms that may be related to the received alarm.
  • the alarm correlator component 700 can search the historical data 308 for previous alarms generated by the same device and/or for the same interface (e.g., over some threshold historical time window, such as the most recent 30 minutes).
  • the alarm correlator component 700 can group the received alarm with other alarms generated by the same device and/or for the same interface within the threshold time window.
  • the alarm generator component 700 can group the received alarm with at least one alarm generated by neighboring devices in the network topology (where the alarm correlator component 700 identifies the neighboring devices through analysis of the network graph 310 ).
  • the alarm correlator component 700 can group the alarm with alarms generated on neighboring devices that are 1 to 2 hops upstream or downstream of the failing device in the hierarchical network topology, and that have been generated within a threshold amount of time from the time that the received alarm was generated.
  • the alarm correlator component 700 can group the received alarm with at least one other alarm generated by one or more devices in a network redundancy group (with the device that generated the alarm) that may be correlated (e.g. illustrating a problem with a failover protocol). It can be ascertained that a group of alarms can be representative of a singular network failure, and different groups of alarms can represent different network failures.
  • the alarm correlator component 700 can attempt to match the alarm with a priority event or a trouble ticket (if present). For example, the alarm correlator component 700 can perform the matching on a variety of fields: 1) network device and/or interface name.
  • a device name is typically coded as aa-bb-cc-dd, where aa is data center, bb is platform name, cc is name of the hosted service or application, and dd is a logical number related to the deployment of the device that generated the alarm; 2) the type of the device, 3) an error message, and 4) event notification time.
  • the alarm correlator component 700 can use a variety of string matching algorithms (e.g., edit distance, Aho-Corasick pattern matching, Levenshtein distance, etc.). This allows for the matching of an alarm with possible matches in the recent past (based on setting a threshold on the notification time).
  • string matching algorithms e.g., edit distance, Aho-Corasick pattern matching, Levenshtein distance, etc.
  • the alarm correlator component 700 can perform the matching based on failures occurring on neighboring devices. Neighbors are determined by analyzing the network graph 310 based on link level connectivity.
  • the alarm correlator component 700 can perform a match based upon the type of network device—e.g. a configuration bug across load balancers in the same data center or across multiple data centers resulting in a large correlated failure.
  • the event prioritizer component 312 also includes a ranker component 702 that ranks groupings of alarms (failure events) for troubleshooting.
  • the ranker component 702 can be configured to prioritize events to minimize negative impact on the data center 100 and/or customers of the data center 100 .
  • the ranker component 702 can prioritize events based upon a failing device being close to a top of a network hierarchy, as such devices pose a relatively high risk of service outage.
  • the ranker component 702 can prioritize events as a function of a number of properties which may be impacted due to the failure of the device. Further, impact of a single property may cause the ranker component 702 to assign a relatively high priority to an event.
  • the ranker component 702 can prioritize events based upon the amount of traffic carried by a failing device. In yet another example, the ranker component 702 can prioritize events based upon an impact on traffic through the data center 100 —e.g. failure of the device may cause significant loss of traffic. In still yet another example, the ranker component 702 can prioritize events based upon a potential redundancy failure. For instance, failure events not masked by intra-device or inter-device redundancy can be relatively highly ranked. Finally, the ranker component 702 can prioritize failure events caused by or impacting a single-legged device. For example, events pertaining to where failover was successful, but which pose a danger of causing a redundancy failure, can be relatively highly ranked. The output of the event prioritizer component 312 is thus a prioritized list of events, such that the operator 126 can prioritize network failures to minimize their impact on hosted applications and services.
  • FIGS. 8-10 illustrate exemplary methodologies relating to resolving network failures. While the methodologies are shown and described as being a series of acts that are performed in a sequence, it is to be understood and appreciated that the methodologies are not limited by the order of the sequence. For example, some acts can occur in a different order than what is described herein. In addition, an act can occur concurrently with another act. Further, in some instances, not all acts may be required to implement a methodology described herein.
  • the acts described herein may be computer-executable instructions that can be implemented by one or more processors and/or stored on a computer-readable medium or media.
  • the computer-executable instructions can include a routine, a sub-routine, programs, a thread of execution, and/or the like.
  • results of acts of the methodologies can be stored in a computer-readable medium, displayed on a display device, and/or the like.
  • FIG. 8 a flow diagram illustrating an exemplary methodology 800 for outputting a plurality of troubleshooting options for use when troubleshooting a network failure is illustrated.
  • the methodology 800 starts at 802 , and at 804 an alarm that is indicative of a network failure is received.
  • the alarm is generated by a device in a data center, which can be a computing device or a network infrastructure device.
  • the alarm can identify the device that is believed to be failing, the device that generated the alarm, an interface on the failing device that is affected, a timestamp that indicates when the alarm was generated, amongst other data.
  • a failing device and/or failing link is identified.
  • the failing device may be the device that generated the alarm or a device in communication with the device that generated the alarm. It is to be understood that when the failing device generates the alarm, it does not necessarily mean that the entire device has gone down. Rather, the alarm could indicate that one of the links of the device has gone down, CPU utilization of the device has exceeded a pre-determined threshold, memory utilization has exceeded a pre-determined threshold, etc.
  • the failure conditions indicated in the alarm are mapped to historically observed failure symptoms, wherein the failure symptoms may have been previously observed as being exhibited by the failing device, by devices related to the failing device, etc. As indicated above, failure history tables can be maintained for respective network devices, which facilitate mapping the failure conditions in the alarm to the possible failure symptoms.
  • a plurality of troubleshooting options are identified, wherein the troubleshooting options are indicative of potential resolutions for curing the failure symptom. Further, the troubleshooting options can have respective labels assigned thereto that are indicative of probabilities of the troubleshooting options curing the failure symptom. The labels can be probabilities or more discreet labels (e.g., high confidence, medium confidence, low confidence etc.).
  • the plurality of troubleshooting options and their respective labels are output for use by an operator to resolve the network failure. As noted above, the labels can be indicative of confidences that the troubleshooting options, when taken by the operator, will respectively mitigate the network failure.
  • the methodology 800 completes at 814 .
  • the methodology 900 starts at 902 , and at 904 an alarm is received that is indicative of a network failure.
  • a query is issued to a database. The query is based upon a time of generation of the alarm, a type of device that issued the alarm, and a location of the device in a hierarchy of the network.
  • results are received based upon the query, the results comprising a second alarm.
  • the alarm is grouped with the second alarm, and at 912 , a ranked list of alarms is output based upon the grouping of the alarm with the second alarm.
  • the methodology 900 completes at 914 .
  • an exemplary methodology 1000 for receiving feedback as to troubleshooting options and/or debugging steps and updating probabilities corresponding to the troubleshooting options and/or debugging steps based upon the feedback is illustrated.
  • the methodology 1000 starts at 1002 , and at 1004 feedback from an operator is received.
  • the feedback can identify 1 ) a network device or link that failed (e.g., including a type of device, a platform of the device, a location of the device in a network topography, etc.); 2) a symptom of the failure; 3) an identity of a troubleshooting option taken by the operator to mitigate the failure; 4) an indication of whether the troubleshooting option successfully mitigated the failure; 5) an identity of a debugging step performed by the operator to mitigate the failure; and 6) an indication of whether the debugging step successfully mitigated the failure.
  • a network device or link that failed e.g., including a type of device, a platform of the device, a location of the device in a network topography, etc.
  • a symptom of the failure e.g., including a type of device, a platform of the device, a location of the device in a network topography, etc.
  • a symptom of the failure e.g., including a type of device, a platform of the device
  • historical data that is descriptive of network failures is updated based upon the feedback.
  • a device failure history table and/or a link failure history table can be updated based upon the received feedback.
  • an alarm is received, and at 1010 the historical data is queried based upon the alarm.
  • the historical data can be queried over several dimensions (e.g., device ID, device type, device platform, link ID, etc.).
  • probabilities for troubleshooting options and/or debugging steps that may potentially mitigate a network failure indicated by the alarm are computed (e.g., in real-time or offline).
  • Such probabilities can be based upon the feedback from the operator, such that probabilities are refined over time as additional feedback is received. Moreover, if the operator were to have taken a troubleshooting option not previously employed in connection with the device, the historical data and/or probabilities can be updated with this new troubleshooting option, which may be later surfaced when a similar alarm is generated.
  • the methodology 1000 completes at 1014 .
  • the computing device 1100 may be used in a system that supports outputting troubleshooting options and debugging steps for curing failure symptoms in a data center.
  • the computing device 1100 can be used in a system that supports prioritizing network failures for an operator.
  • the computing device 1100 includes at least one processor 1102 that executes instructions that are stored in a memory 1104 .
  • the instructions may be, for instance, instructions for implementing functionality described as being carried out by one or more components discussed above or instructions for implementing one or more of the methods described above.
  • the processor 1102 may access the memory 1104 by way of a system bus 1106 .
  • the memory 1104 may also store failure history tables, a network graph, etc.
  • the computing device 1100 additionally includes a data store 1108 that is accessible by the processor 1102 by way of the system bus 1106 .
  • the data store 1108 may include executable instructions, failure history tables, etc.
  • the computing device 1100 also includes an input interface 1110 that allows external devices to communicate with the computing device 1100 .
  • the input interface 1110 may be used to receive instructions from an external computer device, from a user, etc.
  • the computing device 1100 also includes an output interface 1112 that interfaces the computing device 1100 with one or more external devices.
  • the computing device 1100 may display text, images, etc. by way of the output interface 1112 .
  • the external devices that communicate with the computing device 1100 via the input interface 1110 and the output interface 1112 can be included in an environment that provides substantially any type of user interface with which a user can interact.
  • user interface types include graphical user interfaces, natural user interfaces, and so forth.
  • a graphical user interface may accept input from a user employing input device(s) such as a keyboard, mouse, remote control, or the like and provide output on an output device such as a display.
  • a natural user interface may enable a user to interact with the computing device 1100 in a manner free from constraints imposed by input device such as keyboards, mice, remote controls, and the like. Rather, a natural user interface can rely on speech recognition, touch and stylus recognition, gesture recognition both on screen and adjacent to the screen, air gestures, head and eye tracking, voice and speech, vision, touch, gestures, machine intelligence, and so forth.
  • the computing device 1100 may be a distributed system. Thus, for instance, several devices may be in communication by way of a network connection and may collectively perform tasks described as being performed by the computing device 900 .
  • Computer-readable media includes computer-readable storage media.
  • a computer-readable storage media can be any available storage media that can be accessed by a computer.
  • such computer-readable storage media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
  • Disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc (BD), where disks usually reproduce data magnetically and discs usually reproduce data optically with lasers. Further, a propagated signal is not included within the scope of computer-readable storage media.
  • Computer-readable media also includes communication media including any medium that facilitates transfer of a computer program from one place to another. A connection, for instance, can be a communication medium.
  • the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave
  • coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio and microwave
  • the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio and microwave
  • the functionally described herein can be performed, at least in part, by one or more hardware logic components.
  • illustrative types of hardware logic components include Field-programmable Gate Arrays (FPGAs), Program-specific Integrated Circuits (ASICs), Program-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Telephonic Communication Services (AREA)
  • Debugging And Monitoring (AREA)
US14/223,995 2014-03-24 2014-03-24 Identifying troubleshooting options for resolving network failures Active 2034-04-11 US10263836B2 (en)

Priority Applications (8)

Application Number Priority Date Filing Date Title
US14/223,995 US10263836B2 (en) 2014-03-24 2014-03-24 Identifying troubleshooting options for resolving network failures
BR112016020189-2A BR112016020189B1 (pt) 2014-03-24 2015-03-19 Método e sistema de resolução que facilita resolução de falhas de rede em centro de dados
RU2016137896A RU2682018C2 (ru) 2014-03-24 2015-03-19 Идентификация вариантов выявления неисправностей для устранения отказов сети
CN201580015257.7A CN106165345B (zh) 2014-03-24 2015-03-19 促进化解数据中心中网络故障的方法、系统和计算机可读存储介质
PCT/US2015/021360 WO2015148234A1 (en) 2014-03-24 2015-03-19 Identifying troubleshooting options for resolving network failures
JP2016558574A JP6959736B2 (ja) 2014-03-24 2015-03-19 ネットワーク障害のトラブルシューティング・オプションの識別
EP15717299.0A EP3123666B1 (de) 2014-03-24 2015-03-19 Identifizierung von fehlerbehebungsoptionen zur behebung von netzwerkdefekten
US16/357,202 US11057266B2 (en) 2014-03-24 2019-03-18 Identifying troubleshooting options for resolving network failures

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US14/223,995 US10263836B2 (en) 2014-03-24 2014-03-24 Identifying troubleshooting options for resolving network failures

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/357,202 Continuation US11057266B2 (en) 2014-03-24 2019-03-18 Identifying troubleshooting options for resolving network failures

Publications (2)

Publication Number Publication Date
US20150271008A1 US20150271008A1 (en) 2015-09-24
US10263836B2 true US10263836B2 (en) 2019-04-16

Family

ID=52988406

Family Applications (2)

Application Number Title Priority Date Filing Date
US14/223,995 Active 2034-04-11 US10263836B2 (en) 2014-03-24 2014-03-24 Identifying troubleshooting options for resolving network failures
US16/357,202 Active 2034-07-21 US11057266B2 (en) 2014-03-24 2019-03-18 Identifying troubleshooting options for resolving network failures

Family Applications After (1)

Application Number Title Priority Date Filing Date
US16/357,202 Active 2034-07-21 US11057266B2 (en) 2014-03-24 2019-03-18 Identifying troubleshooting options for resolving network failures

Country Status (6)

Country Link
US (2) US10263836B2 (de)
EP (1) EP3123666B1 (de)
JP (1) JP6959736B2 (de)
CN (1) CN106165345B (de)
RU (1) RU2682018C2 (de)
WO (1) WO2015148234A1 (de)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10728085B1 (en) * 2015-09-15 2020-07-28 Amazon Technologies, Inc. Model-based network management
US10904070B2 (en) * 2018-07-11 2021-01-26 Cisco Technology, Inc. Techniques and interfaces for troubleshooting datacenter networks
US10904383B1 (en) * 2020-02-19 2021-01-26 International Business Machines Corporation Assigning operators to incidents
US10917288B2 (en) * 2019-06-25 2021-02-09 Bank Of America Corporation Adaptive edge-shift for enterprise contingency operations
US11057266B2 (en) * 2014-03-24 2021-07-06 Microsoft Technology Licensing, Llc Identifying troubleshooting options for resolving network failures
US11204824B1 (en) 2020-06-19 2021-12-21 Accenture Global Solutions Limited Intelligent network operation platform for network fault mitigation
EP3926891A1 (de) * 2020-06-19 2021-12-22 Accenture Global Solutions Limited Intelligente netzwerkbetriebsplattform zur netzfehlerreduktion
US11294755B2 (en) * 2019-07-05 2022-04-05 Dell Products L.P. Automated method of identifying troubleshooting and system repair instructions using complementary machine learning models
US11295222B2 (en) * 2019-09-24 2022-04-05 We Jump Intelligent Perception Co., Ltd. Machine failure analyzing system and wearable electronic device having machine failure analyzing function
US11501222B2 (en) 2020-03-20 2022-11-15 International Business Machines Corporation Training operators through co-assignment
US11870648B1 (en) * 2023-05-22 2024-01-09 Saudi Arabian Oil Company System and method for systematically managing network devices
US20240179061A1 (en) * 2022-04-18 2024-05-30 Rakuten Mobile, Inc. System and method for auto-commissioning of network device
US12003361B2 (en) * 2020-11-30 2024-06-04 At&T Intellectual Property I, L.P. Data-powered shipwright for network cloud maintenance

Families Citing this family (70)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10791148B2 (en) * 2013-04-29 2020-09-29 Moogsoft Inc. System in communication with a managed infrastructure
US9465685B2 (en) * 2015-02-02 2016-10-11 International Business Machines Corporation Identifying solutions to application execution problems in distributed computing environments
US20160274962A1 (en) * 2015-03-19 2016-09-22 Alcatel-Lucent Usa Inc. Self-Tuning Troubleshooting Scripts
US10374904B2 (en) 2015-05-15 2019-08-06 Cisco Technology, Inc. Diagnostic network visualization
US10536357B2 (en) 2015-06-05 2020-01-14 Cisco Technology, Inc. Late data detection in data center
US9967158B2 (en) 2015-06-05 2018-05-08 Cisco Technology, Inc. Interactive hierarchical network chord diagram for application dependency mapping
US10142353B2 (en) 2015-06-05 2018-11-27 Cisco Technology, Inc. System for monitoring and managing datacenters
US10193742B2 (en) * 2015-10-29 2019-01-29 Kodacloud Inc. Selecting a corrective action for a network connection problem based on historical data
CN106834149B (zh) * 2015-12-03 2019-10-29 中国科学院沈阳应用生态研究所 成刚菌属嗜甲基短杆菌及其在降解磺酰脲除草剂的应用
US10291648B2 (en) * 2015-12-22 2019-05-14 At&T Intellectual Property I, L.P. System for distributing virtual entity behavior profiling in cloud deployments
CN107040395B (zh) * 2016-02-03 2019-11-15 腾讯科技（深圳）有限公司 一种告警信息的处理方法、装置和系统
US10073753B2 (en) * 2016-02-14 2018-09-11 Dell Products, Lp System and method to assess information handling system health and resource utilization
CN107171820B (zh) * 2016-03-08 2019-12-31 北京京东尚科信息技术有限公司 信息传输、发送、获取方法和装置
US10169133B2 (en) * 2016-04-26 2019-01-01 Juniper Networks, Inc. Method, system, and apparatus for debugging networking malfunctions within network nodes
US10289438B2 (en) 2016-06-16 2019-05-14 Cisco Technology, Inc. Techniques for coordination of application components deployed on distributed virtual machines
US10708183B2 (en) 2016-07-21 2020-07-07 Cisco Technology, Inc. System and method of providing segment routing as a service
US10972388B2 (en) 2016-11-22 2021-04-06 Cisco Technology, Inc. Federated microburst detection
US10469603B2 (en) * 2016-12-08 2019-11-05 Lenovo Enterprise Solutions (Singapore) Pte. Ltd. Using a historical record of actions taken by a group of users to identify responsive actions in a computing system
US10331507B2 (en) * 2016-12-21 2019-06-25 Mastercard International Incorporated Systems and methods for real time computer fault evaluation
WO2018127304A1 (en) * 2017-01-04 2018-07-12 Telefonaktiebolaget Lm Ericsson (Publ) Apparatus and method for network incident troubleshooting
US11329864B2 (en) * 2017-01-13 2022-05-10 Lenovo Enterprise Solutions (Singapore) Pte. Ltd. Remote computing system event resolution
US10275296B2 (en) * 2017-01-24 2019-04-30 Wipro Limited Method and system for resolving one or more errors in an enterprise storage system
US10708152B2 (en) 2017-03-23 2020-07-07 Cisco Technology, Inc. Predicting application and network performance
US10523512B2 (en) 2017-03-24 2019-12-31 Cisco Technology, Inc. Network agent for generating platform specific network policies
US10250446B2 (en) 2017-03-27 2019-04-02 Cisco Technology, Inc. Distributed policy store
US10764141B2 (en) 2017-03-27 2020-09-01 Cisco Technology, Inc. Network agent for reporting to a network policy system
US10594560B2 (en) 2017-03-27 2020-03-17 Cisco Technology, Inc. Intent driven network policy platform
US10873794B2 (en) 2017-03-28 2020-12-22 Cisco Technology, Inc. Flowlet resolution for application performance monitoring and management
CN113766035B (zh) * 2017-03-28 2023-05-23 创新先进技术有限公司 一种业务受理及共识的方法及装置
US10680887B2 (en) 2017-07-21 2020-06-09 Cisco Technology, Inc. Remote device status audit and recovery
CN107204883B (zh) * 2017-07-27 2020-09-08 北京小米移动软件有限公司 网络故障处理方法及装置
US10379934B2 (en) * 2017-07-31 2019-08-13 Oracle International Corporation System and method of providing post error analysis for instances of applications in cloud service environments on a per user basis
US11010238B2 (en) * 2017-08-01 2021-05-18 Hitachi, Ltd. Management system of storage system
US10771314B2 (en) * 2017-09-15 2020-09-08 Accenture Global Solutions Limited Learning based incident or defect resolution, and test generation
US10554501B2 (en) 2017-10-23 2020-02-04 Cisco Technology, Inc. Network migration assistant
US10523541B2 (en) 2017-10-25 2019-12-31 Cisco Technology, Inc. Federated network and application data analytics platform
US10594542B2 (en) 2017-10-27 2020-03-17 Cisco Technology, Inc. System and method for network root cause analysis
US11233821B2 (en) 2018-01-04 2022-01-25 Cisco Technology, Inc. Network intrusion counter-intelligence
US10574575B2 (en) 2018-01-25 2020-02-25 Cisco Technology, Inc. Network flow stitching using middle box flow stitching
US10798015B2 (en) 2018-01-25 2020-10-06 Cisco Technology, Inc. Discovery of middleboxes using traffic flow stitching
US10826803B2 (en) 2018-01-25 2020-11-03 Cisco Technology, Inc. Mechanism for facilitating efficient policy updates
US10999149B2 (en) 2018-01-25 2021-05-04 Cisco Technology, Inc. Automatic configuration discovery based on traffic flow data
US11128700B2 (en) 2018-01-26 2021-09-21 Cisco Technology, Inc. Load balancing configuration based on traffic flow telemetry
US10628283B2 (en) * 2018-03-12 2020-04-21 Bank Of America Corporation Deployment tool that corrects deployment errors
US10838948B2 (en) * 2018-04-30 2020-11-17 Hewlett Packard Enterprise Development Lp Switch configuration troubleshooting
US10769006B2 (en) * 2018-07-31 2020-09-08 Cisco Technology, Inc. Ensemble risk assessment method for networked devices
US11200142B2 (en) * 2018-10-26 2021-12-14 International Business Machines Corporation Perform preemptive identification and reduction of risk of failure in computational systems by training a machine learning module
US11200103B2 (en) 2018-10-26 2021-12-14 International Business Machines Corporation Using a machine learning module to perform preemptive identification and reduction of risk of failure in computational systems
US10824528B2 (en) 2018-11-27 2020-11-03 Capital One Services, Llc Techniques and system for optimization driven by dynamic resilience
US10282248B1 (en) * 2018-11-27 2019-05-07 Capital One Services, Llc Technology system auto-recovery and optimality engine and techniques
CA3073463C (en) * 2019-02-21 2023-11-28 Sandvine Corporation System and method for providing a network traffic portal
US11743105B2 (en) 2019-06-03 2023-08-29 Hewlett Packard Enterprise Development Lp Extracting and tagging text about networking entities from human readable textual data sources and using tagged text to build graph of nodes including networking entities
CN110247821B (zh) * 2019-06-04 2022-10-18 平安科技（深圳）有限公司 一种故障检测方法及相关设备
US10691528B1 (en) * 2019-07-23 2020-06-23 Core Scientific, Inc. Automatic repair of computing devices in a data center
US11275664B2 (en) * 2019-07-25 2022-03-15 Dell Products L.P. Encoding and decoding troubleshooting actions with machine learning to predict repair solutions
US11144038B2 (en) * 2019-09-27 2021-10-12 Rockwell Automation Technologies, Inc. System and method for industrial automation troubleshooting
US10686645B1 (en) 2019-10-09 2020-06-16 Capital One Services, Llc Scalable subscriptions for virtual collaborative workspaces
US11477077B1 (en) * 2019-10-30 2022-10-18 United Services Automobile Association (Usaa) Change management system with monitoring, alerting, and trending for information technology environment
CN112910781B (zh) * 2019-12-04 2022-12-06 中国电信股份有限公司 网络故障切换方法、装置、系统和存储介质
US11283671B2 (en) * 2020-02-28 2022-03-22 Hewlett Packard Enterprise Development Lp Handling issues reported by network devices
CN112118248B (zh) * 2020-09-11 2022-06-14 苏州浪潮智能科技有限公司 云平台虚拟机异常流量检测方法、装置、虚拟机及系统
US11593669B1 (en) * 2020-11-27 2023-02-28 Amazon Technologies, Inc. Systems, methods, and apparatuses for detecting and creating operation incidents
CN112508129A (zh) * 2020-12-22 2021-03-16 珠海格力智能装备有限公司 设备的异常处理方法及装置
US11388039B1 (en) * 2021-04-09 2022-07-12 International Business Machines Corporation Identifying problem graphs in an information technology infrastructure network
US11677615B2 (en) * 2021-04-23 2023-06-13 Fortinet, Inc. Systems and methods for incorporating automated remediation into information technology incident solutions
JP7339298B2 (ja) * 2021-05-27 2023-09-05 株式会社日立製作所 情報処理システム及び方法並びに装置
AU2021450034A1 (en) * 2021-06-10 2023-12-07 Nippon Telegraph And Telephone Corporation Analysis device, analysis method, and analysis program
CN114418292A (zh) * 2021-12-14 2022-04-29 国电南瑞南京控制系统有限公司 一种系统级停电检修计划标准工期计算体系的构建方法
US12088347B2 (en) * 2022-04-22 2024-09-10 Bank Of America Corporation Intelligent monitoring and repair of network services using log feeds provided over Li-Fi networks
CN115934390A (zh) * 2022-11-10 2023-04-07 梅赛德斯-奔驰集团股份公司 处理应用程序崩溃的方法、系统和运行应用程序的设备

Citations (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060233114A1 (en) * 2005-04-15 2006-10-19 Microsoft Corporation Method and apparatus for performing wireless diagnsotics and troubleshooting
US20080181100A1 (en) * 2007-01-31 2008-07-31 Charlie Chen-Yui Yang Methods and apparatus to manage network correction procedures
US7600007B1 (en) * 1999-05-24 2009-10-06 Computer Associates Think, Inc. Method and apparatus for event correlation in service level management (SLM)
US20100083029A1 (en) 2008-09-29 2010-04-01 International Business Machines Corporation Self-Optimizing Algorithm for Real-Time Problem Resolution Using Historical Data
US20110029186A1 (en) * 2008-04-02 2011-02-03 Toyota Jidosha Kabushiki Kaisha Failure diagnostic information generating apparatus and failure diagnostic information generating system
US20110191630A1 (en) 2010-01-29 2011-08-04 International Business Machines Corporation Diagnosing a fault incident in a data center
US8041663B2 (en) 2008-02-27 2011-10-18 International Business Machines Corporation Method for predicting problematic configurations and recommending safe configurations
US20120066541A1 (en) 2010-09-10 2012-03-15 Microsoft Corporation Controlled automatic healing of data-center services
US20120233104A1 (en) 2011-03-07 2012-09-13 Cisco Technology, Inc. System and method for providing adaptive manufacturing diagnoses in a circuit board environment
US8332690B1 (en) 2008-06-27 2012-12-11 Symantec Corporation Method and apparatus for managing failures in a datacenter
US8437246B1 (en) 2005-12-30 2013-05-07 At&T Intellectual Property Ii, L.P. Method and apparatus for providing internet protocol call signaling network assurance
US20130232382A1 (en) 2012-03-01 2013-09-05 Microsoft Corporation Method and system for determining the impact of failures in data center networks
US20140068348A1 (en) * 2012-09-05 2014-03-06 Wipro Limited System and method for intelligent troubleshooting of in-service customer experience issues in communication networks
US20140222998A1 (en) * 2013-02-05 2014-08-07 Cisco Technology, Inc. Learning machine based detection of abnormal network performance
US8806550B1 (en) * 2011-11-01 2014-08-12 TV2 Consulting, LLC Rules engine for troubleshooting video content delivery network
US9274902B1 (en) * 2013-08-07 2016-03-01 Amazon Technologies, Inc. Distributed computing fault management
US20160092294A1 (en) * 2013-05-22 2016-03-31 Nokia Solutions And Networks Oy Fault tracking in a telecommunications system
US9411787B1 (en) * 2013-03-15 2016-08-09 Thousandeyes, Inc. Cross-layer troubleshooting of application delivery
US9443196B1 (en) * 2013-09-30 2016-09-13 Emc Corporation Method and apparatus for problem analysis using a causal map
US20160359872A1 (en) * 2015-06-05 2016-12-08 Cisco Technology, Inc. System for monitoring and managing datacenters
US20170116059A1 (en) * 2015-10-27 2017-04-27 Time Warner Cable Enterprises Llc Anomaly detection, alerting, and failure correction in a network
US20170237484A1 (en) * 2016-01-18 2017-08-17 Qoscience, Inc. Method and apparatus for the detection of distortion or corruption of cellular communication signals
US9824403B2 (en) * 2012-08-17 2017-11-21 International Business Machines Corporation Measuring problems from social media discussions
US9888397B1 (en) * 2016-09-16 2018-02-06 Verizon Patent And Licensing Inc. Intelligent network analytics architecture

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2103744C1 (ru) * 1994-10-06 1998-01-27 Третьяков Сергей Александрович Система тревожной сигнализации
JPH08221295A (ja) * 1995-02-13 1996-08-30 Mitsubishi Electric Corp 障害支援装置
JPH08288944A (ja) * 1995-04-18 1996-11-01 Hitachi Ltd 通信設備管理システム
JPH09307550A (ja) * 1996-05-10 1997-11-28 Hitachi Ltd ネットワークシステム監視装置
US5881048A (en) * 1996-11-25 1999-03-09 Mci Communication Corporation Method and apparatus for determining maximum network failure spans forrestoration
JPH10312321A (ja) * 1997-05-12 1998-11-24 Hitachi Ltd オンラインシステム障害解析方法
US6470386B1 (en) * 1997-09-26 2002-10-22 Worldcom, Inc. Integrated proxy interface for web based telecommunications management tools
FI107312B (fi) 1997-10-14 2001-06-29 Nokia Networks Oy Verkonvalvontamenetelmä tietoliikenneverkkoa varten
US7660240B2 (en) * 2002-11-21 2010-02-09 Huawei Technologies Co., Ltd. Method of achieving the network link status penetrate
JP2006085538A (ja) * 2004-09-17 2006-03-30 Nec Fielding Ltd 復旧支援方法及び復旧支援システム並びに復旧支援用プログラム
JP4586528B2 (ja) * 2004-12-22 2010-11-24 セイコーエプソン株式会社 ユーザサポート
CN100433642C (zh) * 2005-03-15 2008-11-12 华为技术有限公司 一种故障定位和故障排除方法和系统
JP4626852B2 (ja) * 2005-07-11 2011-02-09 日本電気株式会社 通信網の障害検出システム、通信網の障害検出方法及び障害検出プログラム
JP5349457B2 (ja) * 2007-04-23 2013-11-20 トムソン ライセンシング ゲートウエイ装置において障害を検出する方法及び装置
JP2010045624A (ja) * 2008-08-13 2010-02-25 Fujitsu Ltd 保守システム
JP2010049551A (ja) * 2008-08-22 2010-03-04 Toshiba Corp 障害監視装置および障害監視方法
JP5439775B2 (ja) * 2008-09-17 2014-03-12 富士通株式会社 障害対応プログラム、障害対応装置、及び障害対応システム
CN102055604B (zh) * 2009-11-05 2012-12-05 中国移动通信集团山东有限公司 一种故障定位方法及其系统
WO2013071125A1 (en) 2011-11-11 2013-05-16 Level 3 Communications, Llc Systems and methods for automatic replacement and repair of communications network devices
US9178778B2 (en) * 2012-03-23 2015-11-03 Avaya Inc. System and method for end-to-end RTCP
GB2500740B (en) * 2012-03-23 2014-07-09 Avaya Inc System and method for end-to-end RTCP
US10263836B2 (en) 2014-03-24 2019-04-16 Microsoft Technology Licensing, Llc Identifying troubleshooting options for resolving network failures

Patent Citations (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7600007B1 (en) * 1999-05-24 2009-10-06 Computer Associates Think, Inc. Method and apparatus for event correlation in service level management (SLM)
US20060233114A1 (en) * 2005-04-15 2006-10-19 Microsoft Corporation Method and apparatus for performing wireless diagnsotics and troubleshooting
US8437246B1 (en) 2005-12-30 2013-05-07 At&T Intellectual Property Ii, L.P. Method and apparatus for providing internet protocol call signaling network assurance
US20080181100A1 (en) * 2007-01-31 2008-07-31 Charlie Chen-Yui Yang Methods and apparatus to manage network correction procedures
US8041663B2 (en) 2008-02-27 2011-10-18 International Business Machines Corporation Method for predicting problematic configurations and recommending safe configurations
US20110029186A1 (en) * 2008-04-02 2011-02-03 Toyota Jidosha Kabushiki Kaisha Failure diagnostic information generating apparatus and failure diagnostic information generating system
US8332690B1 (en) 2008-06-27 2012-12-11 Symantec Corporation Method and apparatus for managing failures in a datacenter
US20100083029A1 (en) 2008-09-29 2010-04-01 International Business Machines Corporation Self-Optimizing Algorithm for Real-Time Problem Resolution Using Historical Data
US20110191630A1 (en) 2010-01-29 2011-08-04 International Business Machines Corporation Diagnosing a fault incident in a data center
US20120066541A1 (en) 2010-09-10 2012-03-15 Microsoft Corporation Controlled automatic healing of data-center services
US20120233104A1 (en) 2011-03-07 2012-09-13 Cisco Technology, Inc. System and method for providing adaptive manufacturing diagnoses in a circuit board environment
US8806550B1 (en) * 2011-11-01 2014-08-12 TV2 Consulting, LLC Rules engine for troubleshooting video content delivery network
US20130232382A1 (en) 2012-03-01 2013-09-05 Microsoft Corporation Method and system for determining the impact of failures in data center networks
US9824403B2 (en) * 2012-08-17 2017-11-21 International Business Machines Corporation Measuring problems from social media discussions
US20140068348A1 (en) * 2012-09-05 2014-03-06 Wipro Limited System and method for intelligent troubleshooting of in-service customer experience issues in communication networks
US20140222998A1 (en) * 2013-02-05 2014-08-07 Cisco Technology, Inc. Learning machine based detection of abnormal network performance
US9411787B1 (en) * 2013-03-15 2016-08-09 Thousandeyes, Inc. Cross-layer troubleshooting of application delivery
US20160092294A1 (en) * 2013-05-22 2016-03-31 Nokia Solutions And Networks Oy Fault tracking in a telecommunications system
US9274902B1 (en) * 2013-08-07 2016-03-01 Amazon Technologies, Inc. Distributed computing fault management
US9443196B1 (en) * 2013-09-30 2016-09-13 Emc Corporation Method and apparatus for problem analysis using a causal map
US20160359872A1 (en) * 2015-06-05 2016-12-08 Cisco Technology, Inc. System for monitoring and managing datacenters
US20170116059A1 (en) * 2015-10-27 2017-04-27 Time Warner Cable Enterprises Llc Anomaly detection, alerting, and failure correction in a network
US20170237484A1 (en) * 2016-01-18 2017-08-17 Qoscience, Inc. Method and apparatus for the detection of distortion or corruption of cellular communication signals
US9888397B1 (en) * 2016-09-16 2018-02-06 Verizon Patent And Licensing Inc. Intelligent network analytics architecture

Non-Patent Citations (11)

* Cited by examiner, † Cited by third party
Title
"Brocade Network Advisor Features Brief for Data Center Networks", Published on: Dec. 8, 2010, Retrieved at: <<http://www.brocade.com/downloads/documents/technical_briefs/brocade-network-advisor-data-center-fb.pdf>>, 73 pages.
"Context Aware Diagnostics and Error Correction", in Journal of IP.com, Dec. 11, 2012, 6 Pages.
"Decision to Grant a European Patent Pursuant to Article 97(1) EPC for European Patent Application No. 15717299.0", dated Jun. 1, 2017, 2 pages.
"International Preliminary Report on Patentability Issued in PCT Patent Application No. PCT/US2015/021360", dated Jun. 13, 2016, 7 pages.
"International Search Report (ISR) & Written Opinion for PCT Patent Application No. PCT/US2015/021360", dated May 28, 2015, 12 Pages.
"Response to the Chinese Office Action for Chinese Patent Application No. 201580015257.7", Filed Date: Mar. 15, 2017, 15 pages.
"Response to the International Search Report (ISR) & Written Opinion for PCT Patent Application No. PCT/US2015/021360", Filed Date: Sep. 9, 2015, 10 Pages.
"Response to the Written Opinion for PCT Patent Application No. PCT/US2015/021360", Filed Date: Apr. 1, 2016, 8 Pages.
"Written Opinion for PCT Patent Application No. PCT/US2015/021360", dated Feb. 3, 2016, 8 Pages.
Wikipedia "data center" pages, retieved using the WayBackMachine from https://web.archive.org/web/20131229120229/http://en.wikipedia.org/wiki/Data_center#Carrier_neutrality, on Dec. 29, 2013. *
Wu, et al., "NetPilot: Automating Datacenter Network Failure Mitigation", in Proceedings of Acm Sigcomm Conference, Aug. 13, 2012, 12 pages.

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11057266B2 (en) * 2014-03-24 2021-07-06 Microsoft Technology Licensing, Llc Identifying troubleshooting options for resolving network failures
US10728085B1 (en) * 2015-09-15 2020-07-28 Amazon Technologies, Inc. Model-based network management
US10904070B2 (en) * 2018-07-11 2021-01-26 Cisco Technology, Inc. Techniques and interfaces for troubleshooting datacenter networks
US11805004B2 (en) 2018-07-11 2023-10-31 Cisco Technology, Inc. Techniques and interfaces for troubleshooting datacenter networks
US10917288B2 (en) * 2019-06-25 2021-02-09 Bank Of America Corporation Adaptive edge-shift for enterprise contingency operations
US11294755B2 (en) * 2019-07-05 2022-04-05 Dell Products L.P. Automated method of identifying troubleshooting and system repair instructions using complementary machine learning models
US11295222B2 (en) * 2019-09-24 2022-04-05 We Jump Intelligent Perception Co., Ltd. Machine failure analyzing system and wearable electronic device having machine failure analyzing function
US10904383B1 (en) * 2020-02-19 2021-01-26 International Business Machines Corporation Assigning operators to incidents
US11501222B2 (en) 2020-03-20 2022-11-15 International Business Machines Corporation Training operators through co-assignment
EP3926891A1 (de) * 2020-06-19 2021-12-22 Accenture Global Solutions Limited Intelligente netzwerkbetriebsplattform zur netzfehlerreduktion
US11714700B2 (en) 2020-06-19 2023-08-01 Accenture Global Solutions Limited Intelligent network operation platform for network fault mitigation
US11204824B1 (en) 2020-06-19 2021-12-21 Accenture Global Solutions Limited Intelligent network operation platform for network fault mitigation
US12003361B2 (en) * 2020-11-30 2024-06-04 At&T Intellectual Property I, L.P. Data-powered shipwright for network cloud maintenance
US20240179061A1 (en) * 2022-04-18 2024-05-30 Rakuten Mobile, Inc. System and method for auto-commissioning of network device
US11870648B1 (en) * 2023-05-22 2024-01-09 Saudi Arabian Oil Company System and method for systematically managing network devices

Also Published As

Publication number Publication date
RU2016137896A3 (de) 2018-09-19
WO2015148234A1 (en) 2015-10-01
US20150271008A1 (en) 2015-09-24
JP2017509262A (ja) 2017-03-30
JP6959736B2 (ja) 2021-11-05
CN106165345A (zh) 2016-11-23
EP3123666B1 (de) 2017-06-28
BR112016020189A8 (pt) 2021-06-29
RU2682018C2 (ru) 2019-03-14
CN106165345B (zh) 2019-11-26
EP3123666A1 (de) 2017-02-01
RU2016137896A (ru) 2018-03-28
BR112016020189A2 (pt) 2017-08-15
US11057266B2 (en) 2021-07-06
US20190215236A1 (en) 2019-07-11

Similar Documents

Publication Publication Date Title
US11057266B2 (en) Identifying troubleshooting options for resolving network failures
US10594582B2 (en) Introspection driven monitoring of multi-container applications
US10769007B2 (en) Computing node failure and health prediction for cloud-based data center
AU2016213726B2 (en) Core network analytics system
EP3467657B1 (de) Intelligentes prioritätssystem für unternehmenswarnungen
US9071535B2 (en) Comparing node states to detect anomalies
US20210012239A1 (en) Automated generation of machine learning models for network evaluation
KR100714157B1 (ko) 컴퓨터 기반 방법, 컴퓨터 판독 가능 기록 매체 및 데이터 처리 시스템
US12040935B2 (en) Root cause detection of anomalous behavior using network relationships and event correlation
CN110178121B (zh) 一种数据库的检测方法及其终端
CN110574338A (zh) 根本原因发现引擎
JP5542398B2 (ja) 障害の根本原因解析結果表示方法、装置、及びシステム
US11531581B2 (en) Event root cause identification for computing environments
US9860109B2 (en) Automatic alert generation
AU2022259730B2 (en) Utilizing machine learning models to determine customer care actions for telecommunications network providers
WO2023129233A1 (en) Performing root cause analysis on data center incidents
US20230195557A1 (en) Apparatuses, computer-implemented methods, and computer program products for improved data event root cause identification and remediation
US11537391B2 (en) Software change analysis and automated remediation
US11356317B2 (en) Alarm prioritization in a 5G telco network
BR112016020189B1 (pt) Método e sistema de resolução que facilita resolução de falhas de rede em centro de dados
US20240356795A1 (en) Root cause detection of anomalous behavior using network relationships and event correlation
KR20240129027A (ko) 운영 지원 데이터 객체의 개선된 선택 및 제공을 위한 장치, 컴퓨터로 구현되는 방법, 그리고 컴퓨터 프로그램 제품

Legal Events

Date Code Title Description
AS Assignment

Owner name: MICROSOFT CORPORATION, WASHINGTON

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:JAIN, NAVENDU;POTHARAJU, RAHUL;SIGNING DATES FROM 20140321 TO 20140324;REEL/FRAME:032512/0359

AS Assignment

Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC, WASHINGTON

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MICROSOFT CORPORATION;REEL/FRAME:034747/0417

Effective date: 20141014

Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC, WASHINGTON

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MICROSOFT CORPORATION;REEL/FRAME:039025/0454

Effective date: 20141014

STCF Information on status: patent grant

Free format text: PATENTED CASE

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 4